Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
Shortcut Learning in Deep Neural Networks
7 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
7
Pith papers citing it
1
external citations · external index
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Smaller self-supervised ViTs localize objects better via attention than larger ViTs, enabling A² to decouple localization from feature extraction for competitive performance on distribution-shifted benchmarks.
CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
idSCD uses semantic correlation descriptors to perform dataset membership inference by comparing learned semantic structures, outperforming baselines in NLI, emotion, and medical text experiments.
A new scale-aware diagnostic framework shows that unconstrained diffusion generative models exhibit structural freezing and instability instead of smooth physical responses under multiscale perturbations.
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
Moirain models use multimodal SFT and DPO to generate novel RNA sequences with superior protein binding affinities in a zero-shot conditional setting.
citing papers explorer
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
$A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones
Smaller self-supervised ViTs localize objects better via attention than larger ViTs, enabling A² to decouple localization from feature extraction for competitive performance on distribution-shifted benchmarks.
-
Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
-
idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
idSCD uses semantic correlation descriptors to perform dataset membership inference by comparing learned semantic structures, outperforming baselines in NLI, emotion, and medical text experiments.
-
Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems
A new scale-aware diagnostic framework shows that unconstrained diffusion generative models exhibit structural freezing and instability instead of smooth physical responses under multiscale perturbations.
-
Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations
DAR replaces GAP with an attention-based aggregation module retrained jointly with the classifier head to disentangle core from spurious features and outperforms DFR on multiple datasets.
-
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
Moirain models use multimodal SFT and DPO to generate novel RNA sequences with superior protein binding affinities in a zero-shot conditional setting.